A scenario-generic neural machine translation data augmentation method
Amid the rapid advancement of neural machine translation, the challenge of data sparsity
has been a major obstacle. To address this issue, this study proposes a general data …
has been a major obstacle. To address this issue, this study proposes a general data …
The neural machine translation models for the low-resource Kazakh–English language pair
The development of the machine translation field was driven by people's need to
communicate with each other globally by automatically translating words, sentences, and …
communicate with each other globally by automatically translating words, sentences, and …
Alibaba-Translate China's Submission for WMT 2022 Metrics Shared Task
In this report, we present our submission to the WMT 2022 Metrics Shared Task. We build
our system based on the core idea of UNITE (Unified Translation Evaluation), which unifies …
our system based on the core idea of UNITE (Unified Translation Evaluation), which unifies …
Guiding ontology translation with hubness-aware translation memory
Ontology, as the foundational architecture for knowledge representation, necessitates
multilingualization to facilitate cross-lingual knowledge sharing, posing challenges that …
multilingualization to facilitate cross-lingual knowledge sharing, posing challenges that …
Identifying light verb constructions in indonesian: a direct translation approach: a direct translation approach
This study aimed to identify light verb constructions (LVCs) in Indonesian based on machine
translation methods, namely binary translation or direct translation. Based on the method …
translation methods, namely binary translation or direct translation. Based on the method …
Domain adapted machine translation: What does catastrophic forgetting forget and why?
Neural Machine Translation (NMT) models can be specialized by domain adaptation, often
involving fine-tuning on a dataset of interest. This process risks catastrophic forgetting: rapid …
involving fine-tuning on a dataset of interest. This process risks catastrophic forgetting: rapid …
Enhancing Machine Translation Experiences with Multilingual Knowledge Graphs
Translating entity names, especially when a literal translation is not correct, poses a
significant challenge. Although Machine Translation (MT) systems have achieved …
significant challenge. Although Machine Translation (MT) systems have achieved …
PORTULAN ExtraGLUE Datasets and Models: Kick-starting a Benchmark for the Neural Processing of Portuguese
Leveraging research on the neural modelling of Portuguese, we contribute a collection of
datasets for an array of language processing tasks and a corresponding collection of fine …
datasets for an array of language processing tasks and a corresponding collection of fine …
Alibaba-Translate China's Submission for WMT 2022 Quality Estimation Shared Task
In this paper, we present our submission to the sentence-level MQM benchmark at Quality
Estimation Shared Task, named UniTE (Unified Translation Evaluation). Specifically, our …
Estimation Shared Task, named UniTE (Unified Translation Evaluation). Specifically, our …
Effective approaches to neural query language identification
Query language identification (Q-LID) plays a crucial role in a cross-lingual search engine.
There exist two main challenges in Q-LID:(1) insufficient contextual information in queries for …
There exist two main challenges in Q-LID:(1) insufficient contextual information in queries for …